Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks175 from public data
- DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene From Sparse LiDAR Data and Single Color Image437
A deep learning architecture that produces accurate dense depth for the outdoor scene from a single color image and a sparse depth, which improves upon the state-of-the-art performance on KITTI depth completion benchmark.
- Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation429
A hierarchical network with recurrent refinement to update disparities in a coarse-to-fine manner, as well as a stacked cascaded architecture for inference and a new synthetic dataset with special attention to difficult cases for better generalizing to real-world scenes are introduced.
- Bundled camera paths for video stabilization410
A novel video stabilization method which models camera motion with a bundle of (multiple) camera paths based on a mesh-based, spatially-variant motion representation and an adaptive, space-time path optimization and introduces the 'as-similar-as-possible' idea to make motion estimation more robust.
- Low-Light Image Enhancement with Wavelet-Based Diffusion Models385
This work presents a wavelet-based conditional diffusion model (WCDM) that leverages the generative power of diffusion models to produce results with satisfactory perceptual fidelity and takes advantage of the strengths of wavelet transformation to greatly accelerate inference and reduce computational resource usage without sacrificing information.
- 354
- NBNet: Noise Basis Learning for Image Denoising with Subspace Projection238
NBNet is introduced, a novel framework for image denoising designed to train a network that can separate signal and noise by learning a set of reconstruction basis in the feature space, and SSA, a non-local attention module designed to explicitly learn the basis generation as well as subspace projection.
- 229
- OMNet: Learning Overlapping Mask for Partial-to-Partial Point Cloud Registration218
OM-Net is presented, a global feature based iterative network for partial- to-partial point cloud registration that learns overlapping masks to reject non-overlapping regions, which converts the partial-to-partial registration to the registration of the same shape.
- 210
- Content-Aware Unsupervised Deep Homography Estimation204
This work proposes an unsupervised deep homography method with a new architecture design that outperforms the state-of-the-art including deep solutions and feature-based solutions.
- DaST: Data-Free Substitute Training for Adversarial Attacks179
This paper is the first to train a substitute model for adversarial attacks without any real data and can achieve competitive performance compared with the baseline models which are trained by the same train set with attacked models.
- MeshFlow: Minimum Latency Online Video Stabilization160
The quantitative and qualitative evaluations show that the proposed technique for online video stabilization with only one frame latency using a novel MeshFlow motion model can produce comparable results with the state-of-the-art off-line methods.
- Deep Constrained Least Squares for Blind Image Super-Resolution144
This paper reformulate the degradation model such that the deblurred kernel estimation can be transferred into the low resolution space and introduces a dynamic deep linear filter module that can adaptively generate deblurring kernel weights conditional on the input and yields more robust kernel estimation.
- Holistic 3D Scene Understanding from a Single Image with Implicit Representation144
This work proposes an image-based local structured implicit network to improve the object shape estimation, but also refine the 3D object pose and scene layout via a novel implicit scene graph neural network that exploits the implicit local object features.
- 136
- 135
- Parallax-Tolerant Unsupervised Deep Image Stitching134
This work proposes a parallax-tolerant unsupervised deep image stitching technique that is parallax-tolerant and free from laborious designs of complicated geometric features for specific scenes, both quantitatively and qualitatively.
- 117
- ADNet: Attention-guided Deformable Convolutional Network for High Dynamic Range Imaging116
This paper presents an attention-guided deformable convolutional network for hand-held multi-frame high dynamic range (HDR) imaging, namely ADNet, and proposes to align the gamma-corrected images in the feature-level with a Pyramid, Cascading and Deformable alignment module.
- 113
- 110
- Depth-Aware Multi-Grid Deep Homography Estimation With Contextual Correlation108
A contextual correlation layer (CCL) is designed that can efficiently capture the long-range correlation within feature maps and can be flexibly used in a learning framework to predict multi-grid homography from global to local.
- OAENet: Oriented attention ensemble for accurate facial expression recognition101
This work proposes an oriented attention pseudo-siamese network that takes advantage of global and local facial information for high accurate FER and has achieved a very appealing performance compared to other state-of-the-art methods.
- Neural Point Cloud Rendering via Multi-Plane Projection100
A new deep point cloud rendering pipeline through multi-plane projections to project features from 3D points onto 2D image domain into a layered volume of camera frustum, such that ghosting effects due to false visibility check as well as occlusions caused by noise interferences are both avoided successfully.
- UPFlow: Upsampling Pyramid for Unsupervised Optical Flow Learning96
This work designs a self-guided upsample module to tackle the interpolation blur problem caused by bilinear upsampling between pyramid levels, and proposes a pyramid distillation loss to add supervision for intermediate levels via distilling the finest flow as pseudo labels.
- NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results94
The NTIRE 2022 challenge was to super-resolve an input image with a magnification factor of ×4 based on pairs of low and corresponding high resolution images and the aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics.
- C3AE: Exploring the Limits of Compact Model for Age Estimation94
This work investigates the limits of compact model for small-scale image and proposes an extremely Compact yet efficient Cascade Context-based Age Estimation model(C3AE), which possesses only 1/9 and 1/2000 parameters and achieves competitive performance.
- Low-Light Image Enhancement with Illumination-Aware Gamma Correction and Complete Image Modelling Network85
A novel Transformer block is proposed to completely simulate the dependencies of all pixels across images via a local-to-global hierarchical attention mechanism, so that dark areas could be inferred by borrowing the information from far informative regions in a highly effective manner.
- FINet: Dual Branches Feature Interaction for Partial-to-Partial Point Cloud Registration82
This work proposes to solve the partial-to-partial registration from a new perspective, by introducing multi-level feature interactions between the source and the reference clouds at the feature extraction stage, such that the registration can be realized without the attentions or explicit mask estimation for the overlapping detection as adopted previously.
- Learning Optical Flow with Adaptive Graph Reasoning81
This work introduces a novel graph-based approach, called adaptive graph reasoning for optical flow (AGFlow), to emphasize the value of scene/context information in optical flow, and can effectively exploit the context information and incorporate it within the matching procedure, producing more robust and accurate results.
- 81
- Motion Basis Learning for Unsupervised Deep Homography Estimation with Subspace Projection79
A new framework for unsupervised deep homography estimation is introduced and results show that this approach outperforms the state-of-the-art on the homography benchmark datasets both qualitatively and quantitatively.
- 76
- 74
- Seamless Video Stitching from Hand‐held Camera Inputs74
This paper presents the first system to stitch videos captured by hand‐held cameras using CoSLAM system and generates a smooth virtual camera path, which stays in the middle of the original paths.
- 72
- Deep Rectangling for Image Stitching: A Learning Baseline72
This paper proposes the first deep learning solution to image rectangling by predefine a rigid target mesh and only estimate an initial mesh to form the mesh deformation, contributing to a compact one-stage solution.
- Automatic Reflection Removal using Gradient Intensity and Motion Cues71
Compared to the existing approaches that require a sequence of images or a video clip for the separation of two photos, this method only needs two images, which largely improves its feasibility.
- Unsupervised Homography Estimation with Coplanarity-Aware GAN69
This work proposes an unsupervised GAN to impose coplanarity constraint on the predicted homography, which is realized by using a generator to predict a mask of aligned regions, and then a discriminator to check if two masked feature maps are induced by a single homography.
- 66
- DIPNet: Efficiency Distillation and Iterative Pruning for Image Super-Resolution64
This work proposes a novel multi-stage lightweight network boosting method that leverage enhanced high-resolution output as additional supervision to improve the learning ability of lightweight student networks and adopts an effective lightweight network training strategy that combines multi-anchor distillation and progressive learning, enabling the lightweight network to achieve outstanding performance.
- BSRT: Improving Burst Super-Resolution with Swin Transformer and Flow-Guided Deformable Alignment61
This work combines optical flows and deformable convolutions, hence the BSRT can handle misalignment and aggregate the potential texture information in multi-frames more efficiently and wins the championship in the NTIRE2022 Burst Super-Resolution Challenge.
- 59
- 57
- Uncertainty Guided Adaptive Warping for Robust and Efficient Stereo Matching54
A novel Uncertainty Guided Adaptive Correlation (UGAC) module is introduced to robustly adapt the same model for different scenarios and a variance-based uncertainty estimation is employed to adaptively adjust the sampling area during warping operation.
- 51
- 49
- DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-based Optimization49
A novel method for panoramic 3D scene understanding which recovers the 3D room layout and the shape, pose, position, and semantic category for each object from a single full-view panorama image is proposed.
- 47
- 46
- UPHDR-GAN: Generative Adversarial Network for High Dynamic Range Imaging With Unpaired Data46
Although the pair data are missing, UPHDR-GAN can properly handle the ghosting artifacts caused by moving objects or misalignments with the help of the modified GAN loss, the improved discriminator network and the useful initialization phase.
- NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results45
This paper reviews the challenge on constrained high dynamic range (HDR) imaging that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2022, and the competition set-up, datasets, proposed methods and their results.
- GAFlow: Incorporating Gaussian Attention into Optical Flow44
This paper introduces a novel Gaussian-Constrained Layer (GCL) which can be easily plugged into existing Transformer blocks to highlight the local neighborhood that contains fine-grained structural information and provides a newGaussian-Guided Attention Module (GGAM) which not only inherits properties from Gaussian distribution to instinctively revolve around the neighbor fields of each point but also is empowered to put the emphasis on contextually related regions during matching.
- NTIRE 2021 Challenge on Burst Super-Resolution: Methods and Results43
The NTIRE2021 challenge on burst super-resolution was to generate a clean RGB image with 4 times higher resolution given a RAW noisy burst as input, and the top-performing methods set a new state-of-the-art for the burstsuper-resolution task.
- 43
- Fast Camera Image Denoising on Mobile GPUs with Deep Learning, Mobile AI 2021 Challenge: Report39
The first Mobile AI challenge is introduced, where the target is to develop an end-to-end deep learning-based image denoising solution that can demonstrate high efficiency on smartphone GPUs.
- 39
- Learning Optical Flow from Event Camera with Rendered Dataset38
This work proposes to render a physically correct event-flow dataset using computer graphics models, and introduces an adaptive density module (ADM) based on which the dataset can adjust the density of events.
- AccFlow: Backward Accumulation for Long-Range Optical Flow37
A novel recurrent framework called AccFlow is proposed, which recursively backward accumulates local flows using a deformable module called as AccPlus, which demonstrates the superiority of backward accumulation over conventional forward accumulation.
- 37
- DMHomo: Learning Homography with Diffusion Models35
This work proposes DMHomo, a diffusion model-based framework for supervised homography learning that effectively overcomes the scarcity of qualified datasets in supervised homography learning and improves generalization to real-world scenes.
- MEFLUT: Unsupervised 1D Lookup Tables for Multi-exposure Image Fusion35
A new approach for high-quality multi-exposure image fusion (MEF), which shows that the fusion weights of an exposure can be encoded into a 1D lookup table (LUT), which takes pixel intensity value as input and produces fusion weight as output.
- 35
- 34
- RecDiffusion: Rectangling for Image Stitching with Diffusion Models33
This work introduces a novel diffusion-based learning framework, RecDiffusion, for image stitching rectangling, which combines Motion Diffusion Models (MDM) to generate motion fields and utilizes a weighted map to identify regions needing correction during each iteration of CDM.
- 33
- Single-Image-Based Deep Learning for Segmentation of Early Esophageal Cancer Lesions32
A novel deep learning approach for segmenting EEC lesions using the so-called “You-Only-Have-One” (YOHO) framework, which achieves a mean Dice score of 0.888, which is much higher as compared to the existing deep-learning methods, thus representing a significant advance toward clinical applications.
- Minimum Latency Deep Online Video Stabilization31
This work adopts recent off-the-shelf high-quality deep motion models for motion estimation to recover the camera trajectory and focus on the latter two steps, and builds a motion dataset that contains stable and unstable motion pairs for the training.
- An efficient and compact 3D local descriptor based on the weighted height image29
The experimental results indicate that the proposed WHI descriptor outperforms the state-of-the-art (SOTA) algorithms in terms of accuracy and efficiency and the compactness of the WHI is about six times more than that of the SOTA algorithms.
- 28
- 28
- 28
- 27
- Stereo RGB and Deeper LIDAR-Based Network for 3D Object Detection in Autonomous Driving27
This paper proposes the Stereo RGB and Deeper LIDAR (SRDL) framework which can utilize semantic and spatial information simultaneously such that the performance of network for 3D object detection can be improved naturally.
- GyroFlow: Gyroscope-Guided Unsupervised Optical Flow Learning26
This work designs a self-guided fusion module to fuse the background motion extracted from the gyro field with the optical flow and guide the network to focus on motion details and shows that this method outperforms the state-of-art methods in both regular and challenging scenes.
- 25
- FlowPolicy: Enabling Fast and Robust 3D Flow-Based Policy via Consistency Flow Matching for Robot Manipulation24
The proposed FlowPolicy refines the flow dynamics by normalizing the self-consistency of the velocity field, enabling the model to derive task execution policies in a single inference step, thus improving the inference efficiency.
- 24
- 23
- Semi-Supervised Wide-Angle Portraits Correction by Multi-Scale Transformer23
The Multi-Scale Swin-Unet (MS- unet) based on the multi-scale swin transformer block (MSTB), which can simultaneously learn short-distance and long-distance information to avoid artifacts.
- 23
- ASFlow: Unsupervised Optical Flow Learning With Adaptive Pyramid Sampling23
This work presents an unsupervised optical flow estimation method by proposing an adaptive pyramid sampling in the deep pyramid network, and proposes a Content-Aware Pooling module, which promotes local feature gathering by avoiding cross region pooling, so that the learned features become more representative.
- Practical Wide-Angle Portraits Correction with Deep Structured Models23
A cascaded network is built consisting of a LineNet, a ShapeNet, and a transition module (TM), which corrects perspective distortions on the background, adapts to the stereographic projection on facial regions, and achieves smooth transitions between these two projections, accordingly.
- Semi-Supervised Coupled Thin-Plate Spline Model for Rotation Correction and Beyond21
The coupled thin-plate spline model (CoupledTPS), which iteratively couples multiple TPS with limited control points into a more flexible and powerful transformation, and a semi-supervised learning scheme to improve warping quality by exploiting unlabeled data is developed.
- RAGO: Recurrent Graph Optimizer For Multiple Rotation Averaging21
This paper proposes a learnable iterative graph optimizer minimizing a gauge- invariant cost function with an edge rectification strategy to mitigate the effect of inaccurate measurements in Multiple Rotation Averaging (MRA).
- 21
- 20
- D2C-SR: A Divergence to Convergence Approach for Real-World Image Super-Resolution19
D2C-SR is presented, a novel framework for the task of real-world image super-resolution with better accuracy and visual improvements against state-of-the-art methods, with a significantly less parameters number and the D2C structure can also be applied as a generalized structure to some other methods to obtain improvement.
- DeepOIS: Gyroscope-Guided Deep Optical Image Stabilizer Compensation19
A deep network is proposed that compensates for the motions caused by the OIS, such that the gyroscopes can be used for image alignment on the O IS cameras, delivering strong robustness and comparable results with a relatively large margin.
- StabStitch++: Unsupervised Online Video Stitching With Spatiotemporal Bidirectional Warps18
A warp smoothing model is presented to produce stable stitched videos with a hybrid loss to simultaneously encourage content alignment, trajectory smoothness, and online collaboration, and StabStitch++ makes no compromise and optimizes both of them simultaneously, especially in the online mode.
- 18
- 18
- 17
- Supervised Homography Learning with Realistic Dataset Generation17
An iterative framework, which consists of two phases: a generation phase and a training phase, to generate realistic training data and yield a supervised homography network and results show that the method achieves state-of-the-art performance and existing supervised methods can be also improved based on the generated dataset.
- Shape Recovery of Endoscopic Videos by Shape from Shading Using Mesh Regularization17
This work proposes a mesh regularization for shape recovery based on cues derived from Shape-from-Shading (SfS), which can well approximate the underlying non-rigid surfaces, rendering temporally-stabilized meshes for 3D video display.
- GyroFlow+: Gyroscope-Guided Unsupervised Deep Homography and Optical Flow Learning16
This work presents an unsupervised learning approach that fuses gyroscope into homography and optical flow learning, which is the first deep learning framework that fuses gyroscope data and image content for both deep homography and optical flow learning.
- Deep Rotation Correction Without Angle Prior16
This paper proposes a new and practical task, named Rotation Correction, to automatically correct the tilt with high content fidelity in the condition that the rotated angle is unknown, and demonstrates that the algorithm can outperform other state-of-the-art solutions requiring this prior.
- ISPDiffuser: Learning RAW-to-sRGB Mappings with Texture-Aware Diffusion Models and Histogram-Guided Color Consistency15
A texture-aware diffusion model that leverages the generative ability of diffusion models to focus on local detail recovery is proposed, and a texture enrichment loss is further proposed to prompt the diffusion model to generate more intricate texture details.
- Automatic Detection of Small Intestinal Hookworms in Capsule Endoscopy Images Based on a Convolutional Neural Network15
An artificial intelligence system with a convolutional neural network to automatically detect hookworms in CE images and it is hoped this high-accuracy, high-speed, and oversight-preventing system will become an important supplement for detecting intestinal abnormalities inCE images.
- Learning to See in the Extremely Dark14
A diffusion-based framework that leverages the generative ability and intrinsic denoising property of diffusion models to restore visually pleasing results from extremely low-SNR RAW inputs, in which an Adaptive Illumination Correction Module (AICM) and a color consistency loss are introduced to ensure accurate exposure correction and color restoration.
- Removing Rain Streaks by a Linear Model14
Compared with several state-of-the-art works, the proposed method can remove rain streaks from a single color image much more efficiently and offers not only a better visual quality but also a speed-up of several times to one degree of magnitude compared to other conventional deraining methods.
- A pilot trial of Convolution Neural Network for automatic retention-monitoring of capsule endoscopes in the stomach and duodenal bulb14
Results indicate that the Convolution Neural Network for automatic retention-monitoring of the CE in the stomach or the duodenal bulb can be used as an efficient auxiliary measure in the clinical practice.
- 13
- PointRegGPT: Boosting 3D Point Cloud Registration Using Generative Point-Cloud Pairs for Training13
This work presents PointRegGPT, the first generative approach that explores realistic data generation for indoor point cloud registration using generative point-cloud pairs for training and designs a depth correction module to alleviate artifacts caused by point penetration during the re-projection.
- 13
- 13
- 12
- Efficient Single Image Super-Resolution with Entropy Attention and Receptive Field Augmentation12
An efficient SR model to mitigate the dilemma between model efficiency and SR performance is presented, which is dubbed Entropy Attention and Receptive Field Augmentation network (EARFA), and composed of a novel entropy attention (EA) and a shifting large kernel attention (SLKA).
- 12
- 11
- 11
- 11
- 10
- 10
- 10
- TrackCam10
This work proposes a system to generate realistic, 3D-aware tracking shots from consumer videos and introduces a pseudo 3D approach for relative depth estimation to avoid expensive 3D reconstruction for improved robustness and a wider application range.
- 9
- 9
- Colorization for Single Image Super Resolution9
A procedure based on image colorization and back-projection to perform color assignment guided by the super-resolution luminance channel is outlined and it is found that this procedure produces better results both quantitatively and qualitatively than existing approaches.
- 8
- Ada-adapter:Fast Few-shot Style Personlization of Diffusion Model with Pre-trained Image Encoder8
The proposed Ada-Adapter is a novel framework for few-shot style personalization of diffusion models that leverages off-the-shelf diffusion models and pre-trained image feature encoders to learn a compact style representation from a limited set of source images.
- 8
- A new single-view 3D pantograph reconstruction aided by prior CAD model8
A novel 3D pantograph reconstruction method based on the single-view scanned data and prior Computer-Aided Design (CAD) model that can reconstruct the complete 3D model with high accuracy has been successfully applied to the anomaly detection and visualization in the pantograph inspection.
- 8
- 8
- Notice of Removal Kernel-free video deblurring via synthesis8
This paper presents a framework that can restore blurry frames effectively by synthesizing the details from sharp frames by developing this kernel-free method that does not require blur kernels, which are needed previously either for deconvolution or convolving with sharp frames before patch matching.
- 7
- Construction and validation of the Dalian emotional movement open-source set (DEMOS)7
This work constructed the Dalian Emotional Movement Open-source Set (DEMOS), the largest multi-view emotional biological motion set based on the whole body, which can be applied in many fields, including affective computing, social cognition, and psychiatry.
- 7
- CodingHomo: Bootstrapping Deep Homography With Video Coding6
This work introduces a novel method leveraging video coding, particularly by harnessing inherent motion vectors present in videos, that outperforms existing state-of-the-art unsupervised methods, delivering good robustness and generalizability.
- Multi-exposure photomontage with hand-held cameras6
This paper proposes to enable a rough registration by a single homography and combine the inputs seamlessly to hide any possible misalignment, and adds some internal constraints when solving the Poisson equation for balancing and improving fusion results.
- 6
- 6
- 5
- Short-Long-Term Propagation-Based Video Inpainting5
A new method to inpaint videos with removed regions based on combining both short-term propagation-based inpainting (STPI) and long-term propagation-based inpainting (LTPI) modules, offering reliable short-long-term source information for inpainting.
- 5
- Single Exposure High Dynamic Range Image Reconstruction Based on Deep Dual-Branch Network5
Extensive experiments show that the proposed dual-branch network can efficiently restore the texture and color of the over-exposed areas, suppress the noise of the under-exp exposed areas, and obtain the HDR image with good contrast, clear details and high structural fidelity of the ground truth image appearance.
- The neural representation of body orientation and emotion from biological motion4
Findings suggest that the conflicted relationship between the neural representation of body orientation and emotion in LING and PreCG when point-light displays were shown, and the different hemisphere play a different role in encoding different body orientation.
- 4
- Thunder: Thumbnail based Fast Lightweight Image Denoising Network4
Extensive experiments have been carried out on two real-world denoising benchmarks, demonstrating that the proposed Thunder outperforms the existing lightweight models and achieves competitive performance on PSNR and SSIM when compared with the complex designs.
- JigsawGAN: Self-supervised Learning for Solving Jigsaw Puzzles with Generative Adversarial Networks.4
- 4
- 4
- Long-Distance/Environment Face Image Enhancement Method for Recognition4
Long-distance uncontrolled environment face recognition accuracy has been greatly improved, up to 98%, 98%, 95% for 60-, 100-, 150-m images after processed by G-Log from original 95%, 89%, 70%.
- 3
- 3
- 3
- 3
- SAM-IQA: Can Segment Anything Boost Image Quality Assessment?3
This paper utilizes the encoder of Segment Anything, a recently proposed segmentation model trained on a massive dataset, for high-level semantic feature extraction and shows that this approach outperforms the state-of-the-art (SOTA) in four representative datasets, both qualitatively and quantitatively.
- GLM-Net3
Experimental results show that the proposed end-to-end global and local motion estimation network GLM-Net can achieve competitive performance in both tasks at the same time, validating the effectiveness of the motion separation.
- Light-Field Raw Data Synthesis From RGB-D Images: Pushing to the Extreme3
An all-software algorithm to synthesize light-field raw data from a single RGB-D input image, which is driven largely by the need in the research area of light- field data compression.
- 3
- 3
- 2
- 2
- 2
- 2
- 1
- DAS: Neural Architecture Search via Distinguishing Activation Score1
A decouple of WOT into two atomic metrics which represent the distinguishing ability of the network and the number of activation units, and explore better combination rules named (Distinguishing Activation Score) DAS, to improve the prediction accuracy of DAS to meet practical search requirements.
- 1
- 1
- 1
- View-Consistent Intrinsic Decomposition for Stereoscopic Images1
This paper proposes a straightforward yet effective framework that enables a high-quality decomposition for stereoscopic pairs and analyzes local and non-local image textures regularized by super-pixels within and across two views to reduce reflectance ambiguity.
- 1
- –
- –
- –
- –
- –
- Exposure Fusion for Hand-held Camera Inputs with Optical Flow and PatchMatch–
A hybrid synthesis method for multi-exposure image fusion taken by hand-held cameras that combines the efficiency of optical flow and the accuracy of PatchMatch and facilitates a high-quality fusion that is free from blurring/ghosting artifacts.
- –
- –
- –
- –
- Uncertain Region Identification for Stereoscopic Foreground Cutout–
This paper presents a method that automatically segments the foreground objects for stereoscopic images by using an MRF based energy minimization for labelling the unknown pixels, which involves both local and global color probabilities within and across views.
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-14. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.